# agents-tree vs Laminar API + MCP (slim)

> agents-tree scores 64.3 (B) to Laminar's 56.8 (C) for agent tracing. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/agents-tree-vs-laminar.md (~4,900 tokens) · this version ~2,830 tokens · JSON https://www.anchorterminal.com/compare/agents-tree-vs-laminar.json · canonical https://www.anchorterminal.com/compare/agents-tree-vs-laminar
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-01
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

agents-tree scores 64.3 (B) on agent readiness against Laminar API + MCP's 56.8 (C), and leads in 3 of 7 scored categories. Laminar API + MCP leads on schema & documentation, agent ergonomics and maintenance & community. Both do agent tracing.

- agents-tree: B 64.3, rank #401 of 1260 · https://www.anchorterminal.com/tools/agents-tree.min.md
- Laminar API + MCP: C 56.8, rank #751 of 1260 · https://www.anchorterminal.com/tools/laminar.min.md
- agents-tree, good for Seeing every coding-agent session and its sub-agents as one tree in a terminal Ahead on Reliability, 60 against 50; Security & auth, 66 against 45; Payments & pricing, 60 against 30. Also No key needed to call it; No incidents deducted, where Laminar API + MCP loses 5 points for them.
- Laminar API + MCP, good for Teams running browser agents who want session replay next to traces, and for agents that read traces through SQL. Ahead on Schema & documentation, 88 against 64; Agent ergonomics, 80 against 73; Maintenance & community, 83 against 63. Also A hosted endpoint, with nothing to install.

| Category | agents-tree | Laminar API + MCP |
| --- | --- | --- |
| Reliability (16%) | 60 | 50 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 64 | 88 |
| Agent ergonomics (13%) | 73 | 80 |
| Security & auth (14%) | 66 | 45 |
| Payments & pricing (10%) | 60 | 30 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 63 | 83 |
| Transparency & trust (7%) | 62 | 64 |

| Fact (where they differ) | agents-tree | Laminar API + MCP |
| --- | --- | --- |
| Kind | Agent framework | HTTP API |
| Vendor | Karel Blavka | Laminar (LMNR AI) |
| Hosted endpoint | no (local only) | `https://api.lmnr.ai/v1` |
| Transports |  | HTTP, Streamable HTTP |
| Auth | None | API key |
| Pricing | Free | Freemium |
| Licence | MIT (Copyright (c) 2026 Karel Blavka) | Apache-2.0 |
| Tools exposed | none | 3 |
| llms.txt | no | yes |
| Last release | 2026-10-08 | 2026-09-23 |
| Terms last updated | couldn't be read | 2026-08-11 |
| Privacy policy last updated | no document linked | 2026-08-11 |
| Customer content may train models | couldn't be read | yes, with an opt-out |
| Terms restrict automated access | couldn't be read | yes |
| Terms restrict benchmarking | couldn't be read | yes |
| Terms or service can change without notice | couldn't be read | yes |
| Arbitration or class-action waiver | couldn't be read | not found in the text |
| Popularity | none | 3.3k stars, 80k npm/wk, 1.7M PyPI/wk |
| Agent reviews | none | 3.5/5 (2) |

Why the edge:
- Payments & pricing, agents-tree +30: agents-tree 60 (Self-hosted rule. No payment protocol (0). Free under MIT with nothing to buy (20). No card or account (20). A person installs it from PyPI with one command and no sign-up (20). 60 in all.); Laminar API + MCP 30 (No x402 (0). Per-GB prices and Signals token prices published without login (20). The Free plan exists with 1 GB and 7 days, but the pricing page doesn't say whether a card is needed, so half (10). A person signs up in a browser to create a project key (0).)
- Schema & documentation, Laminar API + MCP +24: agents-tree 64 (Framework reading, docs a model can follow, as agent-tree was read. `--json` writes one document with `schema_version` 1 and a fixed set of session, agent and detail fields, and model.py types them as dataclasses, but no JSON Schema or field reference is published (14 of 25). README, AGENTS.md and docs/demo are Markdown in the repository; no llms.txt (10). The README says what it shows and reads, has a caveats section per provider (context window inference, internal formats, how running sessions are found), and the command's help says not to run it inside an agent (15 of 20). argparse with choices for --provider and --color, positive-number checks for --window and --interval, and --json refused with --watch (10 of 15). Usage examples for every flag, key and column tables, and errors as messages on stderr with exit code 1, with few error outputs documented (10 of 15). Semver tags and a schema version, no changelog (5 of 15). 64 in all.); Laminar API + MCP 88 (OpenAPI in the docs, and the MCP tools take typed schemas generated from Rust structs (25). llms.txt and Markdown docs (10). The tool descriptions are among the best in the category. `get_trace_context` says when to use it and what to call first, and `query_laminar_sql` carries the table schema, joins and example queries (18). SQL is a free-form string by nature, though `parameters` are typed and trace IDs are UUIDs (10). The SQL API documents its 400, 401 and 429 bodies with examples (13). Monthly changelog without dates per entry, and a `/v1` API (12).)
- Security & auth, agents-tree +21: agents-tree 66 (Harness reading of the framework checklist, as agent-tree and superpowers were read. 30 for what leaves the machine and credentials, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. No credentials, no network code and no runtime dependencies; PyPI releases are built by trusted publishing with no stored token and wait for a maintainer to approve the pypi environment. It reads every transcript of four agent CLIs, prompts included, and the herdr plugin runs the repository's bundled source rather than a PyPI release (26). Read-only by design. SQLite files are opened with mode=ro, nothing is written to an agent's files, and the only writes are a pane mark (directory 0700, file 0600, O_NOFOLLOW) and herdr's config block with a backup and check. It can't act on an agent (17). Control characters and escape sequences are stripped from every transcript field before a view, and the help warns that output run inside an agent lands in its context, but `--json` passes prompts and last messages unredacted with no note that they are untrusted (10). It keeps no state or log of its own. The detail view names each transcript's path, and herdr's config keeps a backup (8). No SECURITY.md, no security.txt and no advisories found; GitHub's security page couldn't be read. CI pins third-party actions to commit SHAs with Dependabot on them (5). 66 in all.); Laminar API + MCP 45 (One project API key as a Bearer token, revocable, scoped to one project, with no read-only key type (20). MCP has no write tools and SQL is SELECT-only on a read-only database client (16). Traces hold application inputs and outputs, and we found no prompt-injection guidance for agents reading them (3). No audit log found (0). SOC 2 Type II and HIPAA are claimed on the pricing page. No SECURITY.md, no security.txt and no published advisories, and the cross-tenant fix below went out as a commit only (6).)
- Maintenance & community, Laminar API + MCP +20: agents-tree 63 (1.2.0 on PyPI on 8 October 2026, 24 days before the check, and a commit on main on 11 October (30). Five PyPI releases between 7 and 8 October 2026 (20). Issue and pull-request replies couldn't be read, as github.com was unreachable. The bare clone shows two Dependabot branches of 28 October unmerged (5 of 25). Not an MCP server and in no official directory; herdr's plugin marketplace couldn't be read (0). No runtime dependencies, a lock file, CI on five Python versions and Dependabot for the workflow actions, with its two updates unmerged (8 of 10). 63 in all.); Laminar API + MCP 83 (TypeScript SDK 0.8.49 on 2026-09-23, Python SDK 0.7.64 on 2026-09-21 and server v0.2.5 on 2026-09-13, with commits on the dev branch on 1 October (30). Five server tags and well over three SDK releases since 3 July (20). We couldn't load issue reply times (10). Both SDKs current (15). Backend build-and-test, frontend build, migration checks and Dependabot. Pass state not checked (8).)
- Reliability, agents-tree +10: agents-tree 60 (Local-package reading, as for agent-tree, superpowers and tokeneconomizer. Installs from PyPI with `uv tool install agents-tree` or pipx, with Python 3.10 or later and POSIX stated in pyproject.toml and Linux and macOS in the herdr manifest (20). .github/workflows/test.yaml runs pylint, pyright, 173 pytest tests, a test run and a package build on Python 3.10 to 3.14 on every push and pull request. Whether the runs pass wasn't checked, as github.com couldn't be read (15 of 25). Issues couldn't be read for the same reason (5 of 25, unchecked). Semver tags and Conventional Commit messages, but no changelog, and the README's caveat that transcript formats may change is the only note on breakage; the switch to reading every provider by default came with 1.0.0 (5 of 15). Version 1.2.0 (15). 60 in all.); Laminar API + MCP 50 (Better Stack page at status.laminar.sh, but its only components are the homepage and an API echo probe, with nothing for ingestion, SQL or MCP (12 of 20). The last 90 days show one planned Postgres upgrade of 30 minutes on 8 August and 99.943 per cent on the echo probe (20, minor only). The docs say queries are rate limited per project but give no numbers (0). The SQL API documents 429 with an instruction to retry with backoff. Nothing for ingestion (8). No SLA found on the pricing page or in the docs (0). API, SQL and MCP are GA (10).)
- Agent ergonomics, Laminar API + MCP +7: agents-tree 73 (Framework reading, how much an agent has to carry. agents-tree adds nothing to any agent's context, since it reads transcripts and never writes to a session. Used through `--json`, it returns every matched agent's prompt and last message with no field selection or size limit (20 of 25). A directory, a session id or unique prefix, `-r` for running only and `--provider` narrow the output, and the live view folds older finished agents; nothing limits the JSON's size (12 of 20). An ambiguous prefix lists the matches, a miss names each provider that found nothing, unknown transcript lines are skipped and missing fields show `-`, and herdr/run.sh names the Python it needs (14 of 20). Read-only, so every run can be repeated; setup-keys strips its own old block, leaves bound keys alone, backs up and restores on a failed `herdr config check` (18 of 20). No arguments shows every running session from every provider, and there are no runtime dependencies; Python only, no SDK applies (9 of 15). 73 in all.); Laminar API + MCP 80 (Three MCP tools, but the SQL tool's description embeds the whole table schema, so the list costs more context than the count suggests (18). Result size is the agent's own `LIMIT` under server-side time, memory and size caps, and `get_trace_context` truncates non-LLM spans (20). Tool failures come back with `isError` and a message. HTTP errors are a single `error` field (17). SQL runs on a read-only ClickHouse client, so retries are safe, but no tool carries `readOnlyHint` and `ask_agent` runs Laminar's own LLM agent (10). One required argument per tool. Python and TypeScript SDKs and a CLI (15).)